Personality Profiling via Browsing Sequence Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for obtaining personality trait scores are time-consuming, expensive, and prone to bias, as they rely on lengthy questionnaires and require explicit consent, with accuracy being questionable due to the potential for deliberate or random responses.
Innovation Solution
A system that aggregates personality trait scores from natural browsing sequences using a machine learning process, specifically a random decision forest, to predict personality trait scores for website audiences, enabling the creation of accurate and reliable personality profiles without explicit assessment, by identifying patterns in anonymous browsing data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional personality questionnaires are used to obtain personality trait scores, then measurement precision may be maintained, but time consumption and complexity increase significantly
Solution Approach 1:
The patent extracts personality trait information from browsing behavior data instead of using traditional questionnaires. The system identifies and extracts relevant features from natural browsing sequences, such as website categories visited, time spent on sites, and navigation patterns, to infer personality traits without requiring users to complete lengthy assessments.
Solution Approach 2:
The patent replaces the mechanical questionnaire-based assessment system with an automated machine learning system that processes browsing behavior data. The random decision forest model automatically analyzes browsing patterns and predicts personality trait scores, eliminating the need for manual questionnaire completion and scoring.
2Measurement precision
If traditional personality questionnaires are used, then personality traits can be assessed, but device complexity and operational complexity increase
Solution Approach 1:
The patent makes the browsing data collection system multi-functional by using the same browsing behavior data for multiple purposes: web analytics, user experience optimization, and personality trait assessment. The random decision forest model is trained on browsing sequences and can predict multiple personality dimensions (openness, conscientiousness, extraversion, agreeableness, neuroticism) simultaneously from the same input data.
Solution Approach 2:
The system enables personality assessment without requiring user participation in the assessment process itself. Users' browsing behaviors automatically generate the data needed for personality profiling, and the machine learning model self-adjusts by training on labeled browsing sequences to improve assessment accuracy over time.
3Quantity of substance
If personality questionnaires are administered, then personality data can be collected, but data reliability decreases due to bias and random responses
Solution Approach 1:
The patent introduces browsing behavior data as an intermediary that indirectly reveals personality traits without requiring users to directly report on themselves. Instead of asking users about their personality characteristics, the system observes their actual browsing behaviors (which websites they visit, how long they stay, what they click on) as a mediator that objectively reflects their preferences and traits.
Solution Approach 2:
The patent replaces the self-reporting mechanism of questionnaires with an automated observation and analysis system that tracks browsing behaviors. The random decision forest model processes objective browsing data (URLs, timestamps, session durations) to infer personality traits, eliminating the subjectivity and potential for deliberate bias inherent in self-reported questionnaire responses.
Data Source
AI summary
Personality aggregation and web browsing is described, for example, to find personality profiles of website audiences for use in recommendation systems, advertising systems, or other web services. In an embodiment natural browsing sequences of users who have given their consent are submitted to a pattern matching process to identify personality trait scores serendipitously occurring in the sequences. In an embodiment, an aggregator combines the personality trait scores by website to obtain audience personality profiles. In an example, a machine learning process carries out the aggregation and enables audience personality profiles of other websites to be predicted. For example, a random decision forest is trained using the natural browsing sequences having identified personality trait scores and once trained, is used to predict personality trait scores of other websites.